Abstract
Metastatic prostate cancer is a clinically and molecularly heterogeneous disease. Under the selective pressure of androgen receptor (AR)–directed therapies, resistant phenotypes frequently emerge, posing significant diagnostic and therapeutic challenges. Neuroendocrine prostate cancer (NEPC) is a clinically important phenotype characterized by lineage plasticity, neuroendocrine features, visceral metastases and poor prognosis. Accurately diagnosing NEPC remains difficult due to its histologic and molecular complexity but has high clinical relevance. In this study, we developed a deep learning model that leverages interpretable cellular features to improve feature extraction from H&E-stained tissue sections (NEURAL-PC). By incorporating a multiple instance learning (MIL) framework, NEURAL-PC enables robust NEPC classification solely from H&E tumor images, achieving an area under the receiver operating characteristic curve (AUROC) of 0.921 in independent external validation. In addition to its diagnostic utility, NEURAL-PC provides prognostic information that enables further subclassification of advanced prostate cancer across diverse datasets supporting its strong prognostic value and generalizability. Broadly, our work highlights a hybrid approach that integrates features across different domains, offering a promising strategy for developing reliable deep learning tools in pathology. Built on this framework, NEURAL-PC represents an extensively validated diagnostic and prognostic model for advanced prostate cancer.
Authors
Zhijun Chen, Erolcan Sayar, Daniela Guevara, Helen Richards, Haoyue Zhang, Radhika A. Patel, Agnes C. Gawne, Lucas J. Liu, Ilsa Coleman, Ruth Dumpit, Colm Morrissey, Michael T. Schweizer, Ruben Raychaudhuri, Laura S. Graham, Evan Y. Yu, Heather H. Cheng, Chien-Kuang C. Ding, Yuzhuo Wang, Peter Choyke, Baris Turkbey, Chantal Chanel-Vos, Christina Fedorov, John R. Otilano III, Troy Kane, Jyothi Manohar, Michael Sigouros, Jones T. Nauseef, Ana Molina, David Nanus, Scott T. Tagawa, Juan Miguel Mosquera, Himisha P. Beltran, Ruth Etzioni, Peter S. Nelson, Rama Soundararajan, Ana M. Aparicio, Cora N. Sternberg, Michael C. Haffner, Stephanie A. Harmon
This file is in Adobe Acrobat (PDF) format. If you have not installed and configured the Adobe Acrobat Reader on your system.
Having trouble reading a PDF?
PDFs are designed to be printed out and read, but if you prefer to read them online, you may find it easier if you increase the view size to 125%.
Having trouble saving a PDF?
Many versions of the free Acrobat Reader do not allow Save. You must instead save the PDF from the JCI Online page you downloaded it from. PC users: Right-click on the Download link and choose the option that says something like "Save Link As...". Mac users should hold the mouse button down on the link to get these same options.
Having trouble printing a PDF?
- Try printing one page at a time or to a newer printer.
- Try saving the file to disk before printing rather than opening it "on the fly." This requires that you configure your browser to "Save" rather than "Launch Application" for the file type "application/pdf", and can usually be done in the "Helper Applications" options.
- Make sure you are using the latest version of Adobe's Acrobat Reader.
